Retinal Vessel Segmentation On Drive

AUC

F1 score

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	AUC	F1 score
iternet-retinal-image-segmentation-utilizing	0.9816	0.8205
deep-learning-architectures-for-diagnosis-of	-	0.8245
bi-directional-convlstm-u-net-with-densley	0.9789	0.8224
study-group-learning-improving-retinal-vessel	0.9886	0.8316
deep-learning-architectures-for-diagnosis-of	-	0.8215
et-net-a-generic-edge-attention-guidance	-	-
g-cascade-efficient-cascaded-graph	-	0.8290
u-net-convolutional-networks-for-biomedical	0.9755	0.8142
sa-unet-spatial-attention-u-net-for-retinal	0.9864	0.8263
rv-gan-retinal-vessel-segmentation-from	-	-
deep-vessel-segmentation-by-learning	0.9802	0.8263
exploring-the-limits-of-data-augmentation-for	0.9855	-
g-cascade-efficient-cascaded-graph	-	0.8210
full-resolution-network-and-dual-threshold	0.9889	0.8316
dunet-a-deformable-network-for-retinal-vessel	0.9802	0.8237
full-scale-representation-guided-network-for	0.9823	0.8322
laddernet-multi-path-networks-based-on-u-net	0.9793	0.8202
ce-net-context-encoder-network-for-2d-medical	0.9779	-
enhancing-retinal-vascular-structure	0.9931	-
road-extraction-by-deep-residual-u-net	0.9779	0.8149
segmentation-of-blood-vessels-optic-disc	-	0.75